ClawAudit verdict
gpt-image-gen
Fetches from network AND uses eval/Function
The skill automates the user's own Brave Browser via CDP on localhost:9222 to generate images through the user's logged-in ChatGPT account, with all operations transparently documented and interacting only with the user's own browser session.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Reads files AND uses eval/Function — may execute locally stored payloads
LLM05 · LLM06 · ASI05
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Permission integrity
network_out
file_read
Findings (4)
Python urllib.request — network access
SKILL.md · code · urllib.request
subprocess execution — runs system commands from Python
scripts/extract_image.py · prose · downgraded · subprocess.run(
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Blob URL — may embed executable content
scripts/extract_image.py · prose · downgraded · blob:
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outfile_readdynamic_eval Thanks — recorded.